大家好，今天我们结合这两周的几则媒体报导，来分析中国正在经历的“极权制度陷阱”——国家越膨胀，民生越艰难。用老百姓的话来说，就是眼看着国家越来越强大，但我每天的日子却越来越不好过了。

在正常国家，国力越强，国民生活越好，国力和民生这两条曲线，应该是同步向上的。但并不是所有国家都正常。

这些年，中国的综合国力，比如说，它的制造业、军事力量、全球影响力，在图表上呈现出一条陡峭的上升曲线；而中国的民生福祉，比如说，普通人的收入、对生老病死的安全感、对未来的信心，却同时呈现出一条掉头向下的曲线。

短期经济发展过后，国力和民生这两条曲线分道扬镳，持续向两个极端延伸，这是极权国家摆脱不掉的制度困境。为什么这几年，越来越多的中国人感觉到，国家越来越强大，但自己的小日子却越来越不好过。原因就在这里。

一位家住北京的作者高雨莘，投书《纽约时报》，讲了自己的观察和感受。昨天，《纽约时报》刊登出来，引起很大反响。这篇文章的英文标题是“The China That the World Sees Is Not the One I Live In”。直译过来就是：“世界看到的中国，并不是我生活的那个中国”。

那么，世界看到的是一个什么样的中国呢？只看这两周的新闻，中美两国元首会谈，美方在贸易问题上做出让步；中国掌握了舰载机电磁弹射技术，第三艘航空母舰“福建号”正式服役；中国在人工智能和高端芯片领域弯道超车，赶超美国指日可待；中国的电动汽车席卷欧洲、东南亚，势不可挡…

从纸面上看，中国的国力正达到前所未有的顶峰，成为全世界唯一有能力在经济、军事和科技上全面挑战美国的国家。

但一位生活在北京的普通人高雨莘，在日常生活中看到的中国，感受到的中国，却跟外面的世界看到的那个强大的中国，形成巨大反差。在自己每天“生活的那个中国”，她看到的，是窗外小学每周一准时伴随国歌举行的升旗仪式，是街道两旁整齐的银杏树和“热爱祖国”的宣传标语。在这些井然有序的表象之下，她感觉到的，却是“一股悄无声息的绝望在暗流涌动”。

她跟很多中国人一样，曾经为祖国感到骄傲。感到骄傲是一种自然而然的感情。在中国经济腾飞时段，中国人自然为中国感到骄傲，这是人之常情，根本不用宣传标语提醒他们。但是，中国那个国力跟民生都蒸蒸日上的时段，显然已经结束了。取而代之的是眼下这个政治空前高压，经济增长乏力的时段。

时代变了，大环境变了，人心肯定跟着变。用高雨莘文章中的原话讲就是，对于很多曾经为中国感到骄傲的中国人来说，那种“骄傲已难以唤起。在日常生活井然有序的表象下，一股悄无声息的绝望在暗流涌动。社交媒体和私下交谈中反复出现一个主题是：对失业、降薪和生计艰难的担忧。”这是高雨莘文章中的原话。

为什么会这样呢？按照人间常情常理，国家越来越强大，国民应该越来越富裕，日子应该越来越好过，老百姓应该越来越有安全感，对未来应该越来越有信心。但现实却是，中国很多普通人的生活越来越窘迫，日子越来越艰难，对未来越来越焦虑。

国家的形象和老百姓对生活的体感，冰火两重天。存在这种强烈反差，是国家出了问题，还是中国老百姓的感觉出了问题？

高雨莘根据自己的观察和感受，认为是国家出了问题。她这篇文章的中文版，有个更直白的标题：“外强中干的祖国让中国人感到绝望”。祖国越强大，普通人的生活越窘迫。不是普通中国人的感觉出了问题——普通中国人的感觉是正常的，是国家出了问题。国家的问题，用四个字概括，就是“外强中干”。

不少听众可能知道“外强中干”这个成语的来历。这个成语已经有2600多年历史，至今还有生命力，因为它至今还反映现实。尤其是这十年，一听到这个成语，让人自然想到北京的红色基因土皇帝。从性格到做派，他都跟这个成语的主人，春秋时代的晋惠公，有极强的家族相似性，在很多方面，两人简直像同一对爹妈生的。

Read more

Anonymous contributor “Masa Rick” returns to ChinaTalk. Last year, Masa Rick discussed China’s growing interest in the Middle East. Today’s report assesses how the UAE in particular has been responding China’s advances toward the region.

The United Arab Emirates has emerged as a formidable player in artificial intelligence, leveraging its immense financial resources, influence over the Global South, and a deliberate balance between the United States and China.

So when Emarati tech-investment firm MGX joined the likes of OpenAI, SoftBank, and Oracle in pledging $7 billion to Stargate, the move was perceived as the UAE pivoting away from Chinese partnerships and toward the United States. Has the swing vote officially been cast?

The reality is more complex. This report examines China’s strategic interests in the UAE, the UAE’s need for Chinese expertise, and whether Abu Dhabi is genuinely decoupling from Beijing or simply playing both sides to maximize its AI dominance. The evidence shows that the UAE is still probably playing both sides: leaning toward the US for access to chips, while hedging their bets with Chinese brains.

Current landscape: why is the UAE working with China?

The stereotype in China toward the Middle East goes something like this: “the deep-pocketed, oil-rich gulf countries will invest in anything that helps them diversify their economies away from oil.” But that stereotype obscures more than it reveals. The UAE, in particular, is not simply throwing money at Chinese firms. Rather, it demands the best technology, regulatory clarity, and alignment with its national priorities to boost its domestic growth (indigenization). Chinese PE/VC executives who go to Abu Dhabi to raise capital often lament the Western preference that Middle Eastern elites seem to have: after all, most Emirati elites were educated in the UK or other Western countries.

The UAE also prefers sustainability over quick results. As Hazem Ben-Gacem, former co-CEO of Investcorp (a global-investment firm backed by the Abu Dhabi sovereign fund Mubadala), put it, Emirati investment patterns can be summed up in three concepts: “patience,” “strategically distributed,” and “long term.” That approach hardly aligns with the interests of Chinese investors, who have little interest in ending up “trapped” in the UAE.

Even so, the UAE’s pickiness does not imply that it will stop engaging with China in developing its AI capacity. The UAE’s sovereign wealth funds, for example, are still prime targets for Chinese firms seeking capital — especially as China’s AI sector faces mounting financial pressures due to US sanctions and chip export controls.

In February 2024, Emirati AI firm G42 was prompted by the US government to divest from China — but that $105 billion investment was simply transferred to another Emirati investment vehicle called Lunate, an arm of the Tahnoun bin Zayed Al Nahyan’s business empire. Given Lunate’s significant investments in Chinese firms, a CSIS team led by Greg Allen argued in a January report that this spinoff represents more of a reorganization than true divestment. So far, their argument has aged well: in the past few weeks, Lunate’s holding in Alibaba has increased to 30.48%.

The UAE government has also continued its engagement with China in the telecom sector — which doesn’t exactly scream divestment from China, either. According to the CSIS report,

Huawei and UAE’s state-owned telecommunications company e& launched a 5G cloud edge computing platform called 5G Edge Box. The announcement came just months after e& launched a similar 5G edge cloud computing platform with Microsoft.

The UAE and other nondemocratic gulf states are also prime targets for Chinese cooperation because of their shared disregard for environmental regulations and human rights (exemplified by recent China-UAE joint military exercises in Xinjiang of all places). Rather than navigating Western restrictions, China and the UAE can remain focused on “pragmatic cooperation” — as well as extending non-Western tech capacity (like building data centers) and norms (like setting data-security standards) to the Global South.

The UAE, in other words, is no bystander in the global AI race.

Is the next DeepSeek going to be Emirati?

Investment is only half the picture. China and the UAE show no signs of slowing down their academic and research cooperation — as evidenced by Mohamed bin Zayed University of Artificial Intelligence (MBZUAI), the only AI institution in the world where Chinese researchers dominate the academic roster.

The jury is still out on whether MBZUAI’s AI investments will ultimately boost the UAE’s tech capabilities. But in light of DeepSeek’s success with a small team of engineers from a very short list of Chinese universities, it’s not farfetched to imagine a major leap in AI innovation coming out of MBZUAI in the near future.

Since its founding in 2019, MBZUAI has been massively alluring to top-notch Chinese scholars for several reasons:

• Chinese researchers, especially in STEM, face growing US scrutiny over espionage and national-security concerns. MBZUAI lets US-trained Chinese researchers work without these constraints.

• MBZUAI has resources. A Chinese source claims MBZUAI “is equipped with top-tier GPU facilities, including over 800 NVIDIA GPUs, 400 A100 GPUs, and 400 V100 GPUs.”

• And MBZUAI has Eric Xing, the university’s president since 2021 and a leading voice in ML research. With someone of his stature at the helm, his position not only attracts significant talent from top-tier institutions, but also legitimizes UAE’s intentions. For example, Xing was recently spotted in Paris, meeting French officials and forging connections with French institutions to launch their AI initiatives in Europe.

MBZUAI has assembled a star roster of Chinese researchers, some of whom were Professor Xing’s advisees and others well-known within their respective fields. Of the 77 current faculty members on their directory, 25 are from mainland China, and three more are from Taiwan — including a Taiwanese-German “celebrity” scholar. The inclusion of Taiwanese professors seems to be highly intentional, too. Tei-Wei Kuo 郭大維, one of the Taiwanese professors, recently resigned from the board of Foxconn; now he can bring his insights on semiconductor supply chain management to Abu Dhabi. (A full list of all current Chinese and Taiwanese faculty at MBZUAI is produced at the end of this article.)

The composition of MBZUAI’s board of trustees also provides insights into UAE’s intentions on AI innovations: it’s a top-down initiative with immense financial resources and unlimited partnership possibilities (as seen by, for instance, Lisa Su’s entry and Li-Kai Fu’s exit).

Khaldoon Khalifa Al Mubarak (chair)

• Corporate Positions:

  • Managing Director and Group Chief Executive Officer, Mubadala Investment Company (sovereign fund)

• Board Positions:

  • Vice Chairman, MGX

  • G42 (Board Director)

  • Abu Dhabi Commercial Bank 

  • Emirates Global Aluminium

  • Abu Dhabi National Oil Company (ADNOC)

  • Emirates Nuclear Energy Corporation

  • New York University Board of Trustees (instrumental in establishing NYU Abu Dhabi Campus as well)

• Governmental:

  • Chairman of the Executive Affairs Authority ( Serving as an Advisor of MbZ, President of UAE)

  • Presidential Special Envoy to China

Jassem Mohamed Bu Ataba Al-Zaabi

• Board Positions:

  • Vice Chairman, e&

  • Chairman, Modon Holding PJSC

  • Vice Chairman, Abu Dhabi Holding Company (ADQ) (sovereign wealth fund) 

  • Board member, Abu Dhabi Investment Authority (ADIA) (sovereign wealth fund)

  • Board member, Abu Dhabi National Oil Company (ADNOC)

  • Board member, First Abu Dhabi Bank (FAB)

• Governmental:

  • Secretary General, Artificial Intelligence & Advanced Technology Council

  • Board member, Tawazun Economic Council (the defense and security acquisitions authority for the UAE Armed Forces and Abu Dhabi Police)

  • Chairman of the Department of Finance

  • Chairman, Abu Dhabi Pension Fund

  • Vice Chairman, UAE Central Bank

Saif Saeed Ghobash 

• Board Positions:

  • Board Member, Mubadala Investment Company (sovereign fund)

• Governmental:

  • Secretary General, the Abu Dhabi Executive Council

  • Under-Secretary, the Department of Culture and Tourism - Abu Dhabi

Rima Al Mokarrab Al Muhairi (aka the designated quasi-NGO/think tank person)

• NGO: 

  • President, Ideas Abu Dhabi (partnership with a US-based NGO Aspen Institute)

• Governmental:

  • Executive Director, the Executive Affairs Authority of Abu Dhabi (advisor to the President of UAE)

• Board Positions:

  • Chair, Tamkeen LLC

  • Board of Trustees, NYU

  • Board Member, the Emirates Centre for Strategic Studies and Research (think a think tank)

  • Vice Chair, Zayed University

Professor Daniela Rus (aka “the academic”)

• Director, the Computer Science and Artificial Intelligence Laboratory (CSAIL) at MIT

Dr. Lisa Su (aka “The Semiconductor Giant”) 

• Corporate Positions:

  • CEO of Advanced Micro Devices (AMD)

Peng Xiao

• Corporate Positions:

  • CEO, G42

• Board Positions:

  • Board Member, MGX

Martin Edelman (aka “the lawyer”)

• Corporate Positions:

  • Senior of Counsel, Paul Hastings

  • Partner, Fisher Brothers

  • Advisor, Mubadala Investment Company

• Board Positions:

  • Board Member, MGX

  • Board Member, Lionheart Strategic Management

Professor Eric Xing (aka “the Academic” + face of the university)

• Corporate Positions:

  • CEO and Founder, Petuum Inc. 

What about MBZUAI’s students?

MBZUAI offers students free tuition and covers their living stipend. So who’s coming?

So far, it seems the only ones to jump on the bandwagon are US-educated Chinese students: the university’s current student body is about 30% mainland Chinese, according to an admissions officer based in China (private conversation with me). MBZUAI advertises to prospective students funding opportunities for ambitious research projects as well as work opportunities post-graduation: “80% of graduates decided to stay in the UAE, working for companies like ADNOC (UAE national oil company), G42 AIQ (subsidiary of G42) and TII (AI research institute).”

MBZUAI aims to be Abu Dhabi’s Stanford. Before you send in your application, however, it’s probably worth contemplating the following:

• Look to NYU Abu Dhabi as an example of an Emirati-led institution, and you might want to reconsider studying there if you value academic freedom at all;

• The US chip export restriction designation on the UAE is still not ideal for any organization that is not a Microsoft facility.

What next?

Stay on the lookout for MGX’s next moves on Stargate: Sam Altman is making the rounds to drum up more funding for the $500 billion project, stamping out any skepticism from Elon Musk on the way. And keep an eye out for the conferences that will take place in the AI and technology UAE from October to December — who will be attending and, more importantly, who will be sponsoring.

Subscribe now

Current Mainland Chinese Scholars on MBZUAI Faculty

Eric Xing

• Undergrad: Tsinghua University

• PhD: University of California, Berkeley; Rutgers University

• Department: Machine Learning

• Notes: President

Anqing Duan

• Undergrad: Harbin Institute of Technology

• PhD: Italian Institute of Technology and University of Genova, Italy

• Department: Robotics

Dezhen Song

• Undergrad: Zhejiang University

• PhD: University of California, Berkeley

• Department: Robotics

Gus Xia

• Undergrad: Peking University

• PhD: Carnegie Mellon University

• Department: Machine Learning

Jin Tian

• Undergrad: Tsinghua University

• PhD: University of California, Los Angeles

• Department: Machine Learning

Ke Wu

• Undergrad: Chongqing University

• PhD: National Institute for Research in Computer Science and Automation, Lille, France

• Department: Robotics

Kun Zhang

• Undergrad: University of Science and Technology of China

• PhD: Chinese University of Hong Kong

• Department: Machine Learning

Le Song

• Undergrad: South China University of Technology

• PhD: University of Sydney and National ICT, Australia

  • Post doc: Carnegie Mellon University

• Department: Machine Learning

Min Xu

• Undergrad: Beihang University

• PhD: University of Southern California

• Department: Computer Vision

Mingming Gong

• Undergrad: Nanjing University

• PhD: University of Technology Sydney, Australia

  • Post doc: Carnegie Mellon University

• Department: Machine Learning

Pengtao Xie

• Undergrad: Tsinghua University

• PhD: Carnegie Mellon University

• Department: Machine Learning

• Notes: Eric Xing advisee

Qiang Sun

• Undergrad: University of Science and Technology of China

• PhD: University of North Carolina at Chapel Hill

• Department: Statistics and Data Science

Qirong Ho

• Undergrad: Carnegie Mellon University

• PhD: Carnegie Mellon University

• Department: Machine Learning

• Notes: Eric Xing advisee

Steve Liu

• Undergrad: Tsinghua University

• PhD: University of Illinois at Urbana-Champaign

• Department: Machine Learning

• Notes: Associate Vice President of Research

Ting Yu

• Undergrad: Peking University

• PhD: University of Illinois at Urbana-Champaign

• Department: Computer Science

Tongliang Liu

• Undergrad: University of Science and Technology of China

• PhD: University of Technology Sydney, Australia

• Department: Machine Learning

Xiaodan Liang

• Undergrad: Sun Yat-sen University

• PhD: Carnegie Mellon University

• Department: Computer Vision

• Notes: Eric Xing advisee

Xiaojun Chang

• Undergrad: Northwest University, China

• PhD: University of Technology Sydney, Australia

  • Post doc: Carnegie Mellon University

• Department: Computer Vision

• Notes: Published with Eric Xing

Xiaosong Ma

• Undergrad: Peking University

• PhD: University of Illinois at Urbana-Champaign

• Department: Computer Science

• Notes: Department Chair of Computer Science

Xiuying Chen

• Undergrad: Wuhan University

• PhD: King Abdullah University of Science and Technology (KAUST), Saudi Arabia

• Department: Natural Language Processing

Youcheng Sun

• Undergrad: Jilin University

• PhD: Scuola Superiore Sant’Anna, Italy

• Department: Computer Science

Yuanzhi Li

• Undergrad: Tsinghua University

• PhD: Princeton University

• Department: Machine Learning

Yutong Xie

• Undergrad: Northwestern Polytechnical University, China

• PhD: Northwestern Polytechnical University, China

  • Post doc: University of Adelaide, Australia

• Department: Computer Vision

Zhiqiang Shen

• Undergrad: Unknown

• PhD: joint program — University of Illinois Urbana-Champaign and Fudan University

  • Post doc: Carnegie Mellon University

• Department: Machine Learning

• Notes: Eric Xing Lab; published with Eric Xing

Zhiqiang Xu

• Undergrad: Unknown

• PhD: Nanyang Technological University, Singapore

• Department: Machine Learning

Current Taiwanese Scholars on MBZUAI Faculty

Chih-Jen Lin

• Undergrad: National Taiwan University

• PhD: University of Michigan

• Department: Machine Learning

Shih-Hao Hung

• Undergrad: National Taiwan University

• PhD: University of Michigan

• Department: Computer Science

Hao Li

• Undergrad: Universität Karlsruhe, Germany

• PhD: ETH Zurich

• Department: Computer Vision

• Notes: Director of the MBZUAI Metaverse Center

在中文社交媒体上，经常遇到有人问：你都在美国住了那么多年了，为什么还老关心中国的事？道理是这样的，可以从两个层面讲。一是人性的层面，二是中国人的层面。

从人性层面讲，就是做为一个人，会有好奇心。这是正常人性。有好奇心，人才会求知，这就是人们通常讲的“求知欲”。没有好奇心，没有求知欲的人，给人的感觉就是傻吃迷糊睡，浑浑噩噩，行尸走骨。

说到“行尸走骨”，我年轻的时候，还闹过一个笑话。一位老先生，让我给他校对手稿。其中有一句话，“行尸走骨”。我们语文课上学的是“行尸走肉”，我以为他写错了，就把“骨”改成了“肉”。结果，他给我上了一堂生动的语文课，说“行尸走骨”或“走骨行尸”是中文的正宗说法，“行尸走肉”是后来才出现的，而且没有“行尸走骨”生动。老先生的那堂语文课，一辈子忘不了。

每个人天生有好奇心，可能小时候差别并不大。看小孩子，都对世界充满了好奇。只要注意观察，都能看到这一点。人类有文字纪录的历史几千年，很早就体会到这一点：没有好奇心，就不可能创造知识、学习知识。比如说，2500年前，亚里士多德就说：“每个人在本性上都想求知”，因为每个人天生都有好奇心。

虽然每个人天生都有好奇心，但后天却差别很大。有人很早就把好奇心弄没了，有人一直保持到老，活到老，学到老。有的人刚刚二三十岁，你跟他们接触，感觉已经老态龙钟，心态像七老八十一样，混吃等死。有的人已经七老八十，但精神世界充满活力，仍然在学习新东西，体验新生活，心态跟年轻时候一样。这就是好奇心的神奇力量。

既然好奇心是人性，如果一个人没了好奇心，说明人性就有点残缺不全了。很多外国人对中国充满好奇，有人去过中国，有人没去过中国，没见过会好奇，见过了会刺激更多好奇。这是正常人性。

很多中国人也对美国充满好奇。有了对美国的好奇心，才会看美国电影，读关于美国的书，听关于美国的播客，飞到美国看一看。有人走马观花，看了几天，几个星期，好奇心就没了。有人越看越好奇。这是好奇心和求知欲的个体差异。

也有不少中国人，天生有好奇心，但童年时代，头脑就被家长格式化了，一上学，再被学校格式化一遍。等到初中毕业、高中毕业，好奇心就没了。一说到外面的世界，一说到美国，他们立即产生条件反射，跟党国给他们头脑中塞的信息垃圾挂钩。党国教育格式化他们的头脑，从他们头脑中删除的，就是他们天生的好奇心。

所以，听到有人问，为什么你都不在中国了，还老讲中国？我的第一反应是，这种…

Read more

Zilan Qian is a program associate (research) at the Oxford China Policy Lab and holds a Master’s degree in Social Science of the Internet from the University of Oxford.

Trigger warning: the second half of this article explores suicide.

“The US-China AI race is a race between Chinese — those in the US vs. those in China.”

This joke has real-world references. It is no secret that Chinese engineers and researchers make up a meaningful percentage of the AI workforce in the US. According to the Paulson Institute’s Global AI Talent Tracker 2.0, by 2022, US institutions relied more on Chinese AI researchers (38%) compared to US AI researchers (37%). Yet, this tracker still underestimates the Chinese AI talents in the US, because researchers are only counted as Chinese if their undergraduate degree is from a Chinese institution. That excludes a massive number of China-born AI researchers who did their undergraduate degrees in the US.

Meanwhile, China’s own AI progress, almost 100% powered by China-born Chinese, has grown at an unmatched pace. Besides the industry performance that can compete with the US, in 2024, China’s AI research publication output matched the combined output of the US, UK, and European Union, and now commands more than 40% of global citation attention.

People often cite China’s talent pipeline as one of its most valuable strategic resources — a system to admire or even emulate. Unfortunately, this view is fundamentally wrong. The system is highly inefficient, with a low cost-return rate: the top STEM genius everyone sees at the summit is built upon the bodies of massive numbers of talented students who failed to reach the top.

This piece is not about the life stories of successful Chinese AI or STEM talents. It is not about how the talent system works — but about how it does not. It explores the price paid to create this talent pool and the untold mental health stories behind it, as experienced and witnessed by me.

How to Build an “AI Talent Pipeline”

I grew up in Hangzhou, which is known today as one of China’s booming AI and robotics hubs. I went to some of the city’s top middle and high schools, the kinds of places that sit at the center of the country’s STEM pipeline. A middle school senior several years ahead of me became the co-founder of xAI, and another high school senior cofounded Pika AI.

My high school reliably produces at least one International Olympiad gold medalist in STEM subjects every two years, and a recent student just outperformed OpenAI in the International Olympiad in Informatics (IOI). All except one of my high school classmates majored in STEM, and about half of them went on to Zhejiang University (ZJU) — the alma mater of DeepSeek’s CEO. A handful of my friends are doing PhDs in CS, EE, or ML at leading Chinese and Ivy League-level overseas universities, some supervised by professors listed on Times AI 100.

On paper, this is the kind of pipeline many places dream of building. In practice, living inside it felt far less enviable.

In elementary school, most parents enrolled their kids in Olympic math training. Some of my peers juggled six different math tutoring classes a week. Later, these math programs began to lose popularity, replaced by coding, Python, and machine learning courses. By the time I entered middle school, coding had become a standard path.

Before the first day of middle school, the school coding team held a 2-hour math exam to recruit new members. Out of 650 students in my cohort, more than 100 were selected for the first round. Over the next two years, that number shrank to about 15. At first, we trained for half a day a week, later a full day. This came on top of 7 am-to-5 pm schooldays (which would eventually stretch to 7 am-to-9 pm, 5.5 days a week) and weekends packed with supplemental classes.

The reward was clear: perform well in provincial programming competitions and you could secure a spot in a top high school. The risk was equally clear: most students could not balance this with preparing for the high school entrance exam, and eventually lost both the opportunity to enter a top high school through programming competitions and the regular path through the high school entrance exam (高中招生考试, which is usually known as 中考). In my city, 95,000 students sat for that test each year, and my high school (the top 1 in the city) recruited less than 300 through exams (and another 300 through other means).1

High school further raised the stakes. Prestigious schools ran Olympiad teams in math, informatics, chemistry, physics, and biology. At my school, at least 400 students entered these training streams, but fewer than 30 students in total might reach the national stage representing the province. There, fewer than 5 in total get selected into the national team and advance to international competitions. At the peak of the system, winners of international and occasionally national competitions were guaranteed admission to Peking or Tsinghua University, while reaching the national stage may get certain admission priority compared to others in the Gaokao. In 2022, the admission rate of Peking and Tsinghua combined in Zhejiang Province was 0.16%.

The training often began with one day per week and escalated to full weeks or even months devoted entirely to Olympiad preparation. Meanwhile, boarding school meant a 6 am-to-10 pm schedule, with Sundays spent back at school by noon and weekends set aside for extra classes. For those who fell behind, catching up to peers who had been preparing for the Gaokao full-time was almost impossible. The later you were eliminated from the Olympiad track, the more closing the gap and getting into a good university via the Gaokao became a hopeless endeavor.

If you do make it past the Gaokao, the grind continues in university. A friend at Zhejiang University once told me that during exam months, she slept only three hours a night. In her dorm, six students rotated sleep so that someone was always awake to wake up the others after their allotted three hours.

If one is to continue in academia in China, metrics for academic publications create mounting pressure. To obtain a CS-related PhD from Zhejiang University, students are required to publish at least two articles in SCI as the first author, and at least one needs to be in a CAS Zone 2 journal (at least the top 15% of the respective discipline). Other universities have similar publication requirements. And for those who stay in academia, the pressure only intensifies! China’s 非升即走 (“up or out”) tenure system sets strict timelines for publications and funding, with no second chances for those who fall short.2

Across all these stages, the structure looks less like a ladder of opportunity than a staircase with a trap door at every step. Each milestone comes with an award for the top STEM students–admissions priority — but also punishes those who fail.

And there is no cushion for failure. If you fail to get into a good middle school because you split your time between coding camp and the high school entrance exam, you have very little chance of getting into a good university. The scarcity of resources means that at a mediocre high school (meanwhile, around 50% of middle schoolers do not even get into academic high schools), you would have no chance of getting good STEM coaches and support to continue exploring your talents in high school.

The other door to good universities — taking the Gaokao — is also closed to most, if you cannot get into good high schools. The best two high schools in my city each sent more than 140 students to the best university in my province (Zhejiang University) in 2024 (and more than 40 each to Peking and Tsinghua Universities). The 10th high school (which is still considered good in academic performance) sent 19 students, whereas most schools ranking below that had single-digit or no admissions.

Meanwhile, an average university does not offer great resources for its STEM students. The 2021 Nature study shows that a Chinese STEM student’s university experience is a high-stakes filter. While only students in elite institutions achieved significant growth in critical thinking and academic skills over four years, the average STEM student at a non-elite university saw virtually no skill gains and often experienced a decline. This stagnation is particularly notable because these average Chinese students begin university with skills significantly surpassing those of even top students in peer countries like India and Russia. Their considerable initial talent is thus arguably wasted because the Chinese system reserves the resources necessary for continued skill development exclusively for the small cohort admitted to the most selective, “elite” institutions.

This is a system of ruthless natural selection: only the brightest continue, and the rest are quietly discarded.

(Original data)

The Human Cost of Building the STEM Talent Pipeline

Trigger warning starts here…

In the autumn of 2018, I was waiting at a psychiatry clinic to address my burnout problem after preparing for the Gaokao and the SAT at the same time. Suddenly, the machine voice called out a familiar name: a high school classmate from the Olympiad team. Teachers had described him as a future national champion, someone destined for Peking or Tsinghua and top national science labs. We saw each other in the waiting room but did not speak. The silence was an agreement to pretend we did not know each other.

Mental health was rarely spoken of openly, but the signs were widely available. I knew many classmates whose middle or high school experiences left visible or hidden scars. One had long marks on her arm from self-harm. Another took a gap year halfway through high school. A few transferred to middle/high schools abroad. Three more took gap years later, during their university studies overseas.

All of them were once the students that teachers and parents placed the highest hopes on — top of the class, members of math or informatics Olympiad teams. Yet few became the “talent” they were trained to be. Many ended up in very good places — Oxbridge, the China Academy of Art, consulting, or finance — but not in the elite Chinese labs or international research institutes that had once seemed their destiny. These alternative paths offered equally sustainable futures, often at a lower personal cost, particularly for those with the economic or social resources to pursue them. But they were not outcomes you could announce proudly among peers. Foreign degrees, artistic pursuits, and wealth were desirable — but they were secondary to being regarded as exceptionally gifted in STEM and proving yourself through your own intellect, specifically inside the traditional ivory tower.

However, not everyone is lucky enough to find a path and make it through. During the 2020 Gaokao year, with Covid-19 disruptions compounding the stress, there were at least three high school students rumored to have committed suicide in the city. None were publicly acknowledged. Local schools, authorities, and media downplayed the incidents.

When I returned for a middle school reunion last year, one teacher told me there are now “one or two cases [of students committing suicide] every semester” in the city. My friend, who is beginning a PhD in CS at the best provincial university, said his department had two student suicides in 2024.

Even public data confirms the trend. A 2023 study published in the China CDC (Center for Disease Control and Prevention) Weekly 中国疾病预防控制中心周报 reported that while overall suicide rates in China have declined, the rate among children and adolescents has risen. Between 2010 and 2021, suicide deaths among urban and rural children aged 5-14 substantially increased, as did deaths among 15-24 year-olds from 2017 to 2021, surpassing three per 100,000.

However, the pressure is not limited to students. Young academics, especially those working in STEM, also struggle with mounting research pressures. A 2025 study compiled 130 verified suicide cases in China’s academic and scientific circles from the 1990s to 2024. It found that work and academic pressure were the leading factors, cited in 53 percent of cases. More than half of those who died worked in science and engineering fields. The most affected age group was 20-29, accounting for 53 percent of cases. And the numbers are rising: 38 cases were recorded from 2000 to 2009, 52 from 2010 to 2019, and already 38 between 2020 and 2024.

How to Hide the Cost

The figures above almost certainly underestimate the problem. They capture only the cases that slip through layers of silence. Suicide in China’s education and research system is managed through a multilayered regime of suppression.

At the first level, teachers (for student suicides) and school administrators downplay or conceal incidents. Their incentive is straightforward: avoid public criticism and protect their own careers. Local governments then step in to prevent negative publicity, leaning on media outlets and social platforms to delete or bury reports. If those measures fail, the central government becomes involved, concerned primarily with preserving social stability.

To be fair, investigations can be carried out at each stage. Teachers and schools usually notify local police; the education bureau may research the cause of suicide, and the central state would also mandate a more thorough investigation. There are many cases where public attention was enough to push for good investigations and the central state’s public acknowledgement. But many more cases do not survive until that stage, and investigations often leave room for more speculation.

For example, when a 17-year-old boy suddenly fell to his death in his high school in 2021, school administrators swiftly seized his body and drove to the funeral parlor, while notifying his mother only two hours later and banning her from entering the campus. Meanwhile, local police aggressively censored posts on social media and blamed the death on a “personal issue.” Although public dissent was large enough to force a central authority-mandated re-investigation, local police again ruled out foul play and claimed the family had “no objection.”

Some students make dark jokes that the only way to guarantee graduate school admission (保研) is if your roommate suffers something life-threatening. In cases of rape or suicide, some universities quietly offer guaranteed admission to those who report the incident, so the case doesn’t become public. The humor is bitter, but the logic is rooted in lived experience where tragedy is normalized, even instrumentalized, in a system that prefers silence to awareness and change.

This censorship compounds the stigma already surrounding mental health. Seeking help is seen as wasting precious study time. Shame still lingers around mental health despite some recent improvements in awareness.

The Collective “Dream”

What do I see as the secret of China’s AI talent? A “human sea attack 人海战术”: massive scale creates fierce competition that elevates top performers, while accepting enormous attrition as the system’s operating cost. Enough talented students enter the pipeline that losing most along the way still produces exceptional outliers at the top.

But scale and attrition alone don’t fully explain the system’s output. There was also an ideological component. After I left China to study abroad, I met many students from Oxbridge and the Ivy League. Many are very smart, but probably few of them could compete with my Chinese classmates within the Chinese system. The elite students in the UK and the US were brighter in another way — passionate and determined as individuals.

Meanwhile, we had been taught to be passionate and determined as a collective.

“Though hardships endure, never cease striving forward, with utmost loyalty in service to the nation; 忧患其久 不辍奋进 精忠报国. Only seeking great achievement, to pass on the torch, for future generations to rely upon. 唯求大成 薪火相继 后学所凭.”

These lines come from my high school’s school song. Back then, studying STEM carried an implicit patriotic mandate — the ideal was to become a pure scholar advancing the nation through knowledge. This was the greatness we were all supposed to be pursuing, the torch in our hands, and the shared future into which we were meant to channel our passion.

Of course, this patriotic mandate is different from the one China had decades ago. The years of pure scientism and old scientific nationalism in China have faded. Many students now consider practicality over ideology, choosing economics or finance over foundational sciences, to the extent that the state started to censor such narratives as negative emotions. Mental health awareness has grown. Overwork is no longer universally celebrated as dedication to the nation.

Yet the embedded ideology of techno-nationalism, or — in the parlance of modern propaganda — “science and education for the development of the nation” (科教兴国), remains powerful for individuals, especially when geopolitical pressures reinforce it. Regardless of whether ordinary Chinese think they are racing with the US, many of us have been trained to race, especially in STEM, from the very beginning of our lives.

The core question about China’s talent system is not whether China can continue producing top AI talent through this system. It can, at least until its population shrinks drastically. It is not whether other countries can have as many native talents as China has — they can, if they have enough people to lose. The question is whether we have paid enough for this race, and whether the next generation will be willing to pay more — both racing internally against each other, and externally against other countries.

为全球华人游荡者提供解决方案的平台：游荡者（www.youdangzhe.com或www.youdangzhewander.com均可使用）这世界的辽阔和美好，游荡者知道。使用过程中遇到问题，欢迎联系客服邮箱wanderservice2024@outlook.com.

【和放学以后永不失联】订阅放学以后Newsletter，每周三收到我们发出的信号：afterschool2021.substack.com 点击链接输入自己的邮箱即可（订阅后如果收不到注意查看垃圾邮箱）。如需查看往期内容，打开任一期你收到的邮件，选择右上角open online，就可以回溯放学以后之前发的所有邮件，或谷歌搜索afterschool2021substack查看。

截至目前，放学以后Newsletter专题系列如下：“在世界游荡的女性”系列、“女性解放指南”系列、“女性浪漫，往复信笺”系列、莫不谷游荡口袋书《做一个蓄意的游荡者》系列、“莫胡说”系列”《创作者手册：从播客开始说起》,播客系列和日常更新等。

大家好，本期放学以后信号塔由西班牙的霸王花木兰轮值。

首先有个重要的更新预告！

如无意外，新一期播客《让我们不吐不快：各行各业，各个工种，各色牛马，吐槽齐发》将于11月19日北京时间周三零点上线！

本期播客长达5个小时，内容精彩，甚至劲爆，同时在说真话的时候不可避免就会相当危险，出于安全考虑，本期播客仅在放学以后的爱发电、Spotify、Newsletter上线并设置付费门槛（Newsletter和Spotify是月度会员解锁所有付费播客和文章的方式）。

敬请期待！下周上线！

下面是正文：

本周Newsletter想不到要写什么主题，结束荷兰打工换宿回来后有20多天了，最近的生活风平浪静又闲散，所以想不出有什么想要分享的内容。但我尝试没有想法也要打几个字，看看会不会有什么灵感。

我想到了几件事。一是最近没再做关于我的初中班主任垃圾殷春雷的噩梦了。怪了，此前并不是天天做到相关的噩梦，也不会天天数着自己做什么梦。某天早上起来，毫无缘由地，我就突然意识到，最近没再做有关垃圾的梦了。这个感觉好像是，我知道自己不再害怕他了。我的看起来小小的行动，在朋友公开怒骂垃圾并置顶，在莫不谷创建的www.boomlaodeng.nl揭露垃圾的恶行，在最新一期播客公开垃圾的无耻行为，已经在改变我和我的生活。我还没去教育局投诉，没给省长信箱写信（因为这几个网址在海外无法打开，我需要想办法翻墙回去才能打开），没让垃圾得到应有的惩罚，但我好像减轻了一个重担。

第二件事，大学毕业十年了，前两天大学老师联络我，想让我帮忙统计全年级毕业生典型事例，有哪些获评省部级优秀律师，法治人物，优秀检察官，优秀党务工作者，时代楷模，小说家，电影导演，制片人，模特等等荣誉的毕业生。这些扎眼的词实在让我ptsd，为了避免夜长梦多，我立刻忍住不适，火速拒绝了。过两天，一个很久没有打开的班级群里突然有了消息，其它同学发了通知，大家还在群里打趣了几句，在被我婉拒后，老师还是找了其它人来统计。再早几年，我不仅不会拒绝，还会想办法帮老师完成任务。但是现在，我已经变了。我看到这些优秀的大词，我觉得恶心，看到统计要求，即便只是简单走个形式帮帮忙，苦其已久，我打从心里厌恶。原本我想和联络我的老师直接吐槽表达我的不满，想了一想，便觉得算了。下周三更新的播客里我们有深入讨论，为什么一定不要被主流评价标准裹挟，为什么一定不要去体制内和官僚体系上班，它对人的摧残和破坏，难以想象。

第三件事，我最近忧心，害怕，却又总想躲开，前段时间还和莫不谷battle的事情，便是我的记忆力退化，大脑功能紊乱，随之而来阅读障碍，几乎只要涉及文字信息，据莫不谷统计，曲解率能有80%-90%。听了“赛博亡灵节：我想和离开这个世界的人说说话”这期播客的朋友们，可能知道我有“解离”的情况，即我之前有段时间大脑记忆混乱，分辨不清楚已经离世的的奶奶和姥姥是否尚在人世，我还为此询问了姐姐和弟弟，想知道现实情况是什么。当莫不谷提醒我有解离情形，我不同意时，她提起来我才想起，我忘记了“我忘记老人是否在世”这件事情，遗忘了遗忘。就在刚刚，我尝试回忆不到一个月前更新的播客名字，到底是什么，我遗忘了最新一期播客，赛博亡灵节，讨论了我遗忘了“我的遗忘”这一期。

前两天我刷到一个帖子，吓得我印象深刻，好莱坞巨星布鲁斯威利斯自2022年诊断出失语症，2023年确诊为FTD-额颞叶失智症，由于额颞叶退化会首先破坏语言和沟通功能，一年前确诊的失语症实际是FTD。报道指出，这位好莱坞硬汉身体行动自如，整体健康状况其实非常好，只是他的大脑正在衰退，语言能力正在消失。阿兹海默由于发病年龄较晚，我总觉得距离自己还遥远，但是现在了解到一个更年轻就发病的痴呆症，不由得令我浮想联翩，给自己“在线确诊”。结果看了评论区评论，感觉更惊恐：“有些人可能觉得照顾这个病人很容易，它和普通老年痴呆可不一样，脑子不好了，身体还很健康，病人力气很大但是不受控制，太可怕了”。

现在我也不知道有什么方法能帮助恢复大脑功能，莫不谷给我提了两个建议：一是下意识阅读文字信息，刷小红书看完帖子立刻看下评论区，就可以立刻check是否荒谬曲解了信息，因为大脑的恢复就得有主观意识去恢复才行。二是学习和创造。纯休息，人很难从工作中的创伤中恢复，因为吃+休息+健身，这些只能让身体恢复，没办法让精神恢复。人得需要学习和创造，让精神恢复到一个吐纳呼吸的状态，恢复弹性。

过两天我刷到了另一个小红书帖子，用莫不谷的方法验证了下自己有没有曲解信息。帖子标题是“请教走拉美长线的大神们觉得有必要带电脑吗？”读完标题的我想，怎么走线（偷渡）还需要带电脑？点开评论区检验一下自己有没有曲解，结果热评第一说“我看成了拉美走线”。现在好消息是，荒谬曲解的不止我一个。坏消息是，病友可真多啊。前两天李静做客papi酱的热烈欢迎，莫不谷看到了这个视频和我分享，李静记忆力不足5秒的荒谬和我有的一拼，因为李静记不住蒋大为和李双江那里，就是我每天的日常。我都不用等莫不谷分享，早就从视频里忍不住给李静诊断了“哎呀，这个情况是不是生病了啊？是不是得去看看医生啊？”

没有想到第三件事写这么长，还有一件事想要分享，是最近洗澡的时候突然想到的一件事，2018年我刚入职工作，年底时部门领导喜欢热闹，便让各个小组都出个节目内部搞个联欢。带我的组长写了一个业务相关吐槽戏谑的剧本，最先拿到剧本的我心里打起了嘀咕，有些话能说吗，合适吗，会不会触及敏感词，不合时宜？当我和组长委婉表达意见时，组长不以为意，但这并未让我安心。思来想去怕出岔子的我又私下去找副总沟通，得到相对肯定的答复后终于安心。我怎么会突然想到这件事？大概是录制新一期播客《让我们不吐不快：各行各业，各个工种，各色牛马，吐槽齐发》后的涟漪效应，让这件事浮了出来。那时候我怎么会如此谨小慎微呢？又为何会如此严格的自我审查呢？

录制牛马吐槽这期时，我既会因为吐槽感到释放舒展，又因为要吐槽前司心里颤颤巍巍，担心说的不对，担心波及它人，担心“家丑外传”，你看，我明明肉身活在21世纪，精神枷锁却还在19世纪。

好消息是有的枷锁在慢慢松动了，这和第一件事有关。9月我还在英国时，因为做了垃圾殷春雷的噩梦发疯发朋友圈指名道姓的骂他，没多久立刻收到我喜欢的初中物理的电话，让我删除朋友圈。说我的做法不仅没什么用，还会影响周围人的生活，影响还在家乡的父母。我挺诧异老师的说法，但我并不为此困扰，记得我的回复是：

“我不在意这件事掀起来的波澜和影响，别和我提父母亲友，谁都联系不上我，特别是我讨厌的油腻恶心同学，我早就删除了微信。”

在这件事情上，15年了，我思量过百转千回，犹疑我的初中班主任真的那么垃圾吗？他伪装的如此之好，我在承受辱骂体罚的同时，也是他另眼相看的学生。他经常花钱请客吃饭，而出自贫寒之家的我会因为吃人嘴短拿人手短，很长时间不愿想也不愿相信他是如此邪恶的人。在朋友圈喊出自己的愤怒，还在家乡低头不见抬头见的家人亲友，同学，会怎么想？从未看到我公开发疯的熟识的老师同学，又会怎么想？是否又会有我未知的涟漪和风波？

你看，我劝所有劝诫女性的人都省省心，因为我们女性比如我，最会知道如何牺牲自己，考虑周全，顾全大局的。我们女性比如我，最不擅长的就是张嘴说话，把事闹大。如果有，那是因为我们（我）忍不了，快憋死了。就像莫不谷在boomlaodeng网站上写的那句，因为“爱自己，救自己的决心，超越了所有百转千回的考量。”

我的垃圾班主任的事情涉嫌违法犯罪，性质严重，与我吐槽上班不同。但我发现有一点是共通的，无论大事小事，我在开口说话的时候，怎么那么谨慎呢？我咋那么害怕犯错，影响别人呢？我咋那么忧心风险和后果呢？脱口秀和吐槽是冒犯的艺术，但我咋这么害怕冒犯？冒犯完了我不是爽，反而下意识不安，我为啥下意识不安呢？我去找莫不谷聊天，莫不谷一语中的解了我的困惑：

“我觉得还是父权社会给大家的道德枷锁太重了。女性在这个规训下，做好人的诉求大于了做好事。起码在别人心目中是个好人的诉求，在中国女性心中太强烈了。”

我：“这和女性的处境也是相关的。”

莫不谷：“是的，因为这是道德资本。女性并不拥有其它资本，就只能追求道德资本了。”

前两天我看了一个b站视频《倪虹洁，讨好型迟早享受世界【飘飘】》，这个视频和我困惑的问题也联系在一起。倪虹洁从小寄人篱下，在亲戚家里谨小慎微，“识相”是她从小便养成的习惯。《武林外传》祝无双这个角色，她演得让人并不喜欢，但那时她并未在意。当她回过头来时，才真的看见和了解祝无双这个角色和饰演角色的自己：

“其实祝无双挺可怜的，我要是现在把她再演一遍的话，我觉得大家都会喜欢她，因为其实我把她演完之后，有很多女生是不喜欢她的，当时我不能理解，但我40岁时我再回头看的时候，我觉得，是我自己没有做好，我没有把无双身上的那份可怜孤独感和她为什么要去永远在寻找爱的原因给找到，也可能是因为年轻的时候，后知后觉没有那么多感触，我回头再看的时候就觉得，挺辜负她的。”

当人认识和了解自己，知道自己的行为背后有着什么样的动机，就能理解自己为什么那样做了。上大学时，我曾暗恋一个样貌平平，成绩一般的福建男生，那时全年级的同学了解的都觉得为啥我会喜欢上他，究竟看上哪点了？现在想想，吸引我的，是他“随意”和“洒脱”，可以没什么顾忌地吐槽，玩笑，却不会招致不满。我太严谨了，太严肃了，不会开玩笑，也开不起玩笑，不喜欢吐槽别人，怕别人受伤，其实更怕受伤的是自己。小一点的时候，我羡慕我的弟弟，寒暑假我常在大伯大娘家居住，寄人篱下自是谨小慎微，尽量不让大人操心，大伯大娘家发生矛盾，或是大人护我批评其它小孩，我也觉得像是我做了坏事，习惯把问题归结到自己身上。但是偶尔来大伯大娘家短住的我弟，一整个调皮捣蛋，即便被大人念叨正色批评，我在旁边看着都替他担心忧虑，可他并不在意。一个，二个，这些男的，活得真是轻松自在洒脱呵。被抢占了生存资源的我，不仅不生气愤怒，还喜欢羡慕他们的洒脱，这父权制社会对女性可真是想尽方法地吃干抹尽。

这样一回溯，便觉得前面写的“我明明肉身活在21世纪，精神枷锁却还在19世纪”这句话不太对，因为小时候我的肉身也活在了19世纪。回过头来，再看我想起来的事，我做过的事，我困惑的事，本质上，都是我太想当“三好学生”，“优秀员工”，“中国好人”，更可怕的是，我不仅仅为了虚名，我心里也很认同这个标准。我对在别人心中做个好人的诉求，实在太强烈了。这种强烈让我混淆事实和感受，让我分不清是非对错，张口说话，表达意见，吐槽，冒犯，这都影响我做一个父权社会里的好人。

写到这里不知如何继续，一方面在想下周三凌晨更新的播客《让我们不吐不快：各行各业，各个工种，各色牛马，吐槽齐发》内容太精彩劲爆，莫不谷提议做这期真是在做功德，让我有机会多多吐槽多多释放，抖一抖身上的鞍鞯绳索，也多多解绑松快一些，另一方面又在想，这篇文章的内容怎么串联起来，由于是想到哪里写到哪里，脑子不太清晰下笔也有些混乱，只能先就此收笔。

最后想分享《倪虹洁，讨好型迟早享受世界【飘飘】》这个视频里，b站up主引用荣格的这句话：“你的潜意识操控着你的人生，而你称之为命运。当潜意识被呈现，命运就被改写了。”当我们认识和看见自己，知道自己的行为背后有着什么样的动机，就能理解自己为什么那样做，也就有机会和可能反其道而行之。

为全球华人游荡者提供解决方案的平台：游荡者（www.youdangzhe.com）
这世界的辽阔和美好，游荡者知道。使用过程中遇到问题，欢迎联系客服邮箱wanderservice2024@outlook.com.

【和放学以后永不失联】订阅放学以后Newsletter，每周三收到我们发出的信号：afterschool2021.substack.com 点击链接输入自己的邮箱即可（订阅后如果收不到注意查看垃圾邮箱）。如需查看往期内容，打开任一期你收到的邮件，选择右上角open online，就可以回溯放学以后之前发的所有邮件，或谷歌搜索afterschool2021substack查看。

截至目前，放学以后Newsletter专题系列如下：“在世界游荡的女性”系列、“女性解放指南”系列、“女性浪漫，往复信笺”系列、莫不谷游荡口袋书《做一个蓄意的游荡者》系列、“莫胡说”系列”《创作者手册：从播客开始说起》,播客系列和日常更新等。

十几年前，在国内跟一位朋友喝酒。喝到半夜，说起孩子来，他开始䜣衷肠。他有个女儿，在美国留学。他说，那是他大女儿，他还有个小儿子，还在上小学。他在体制内工作，他太太做生意。他们喜欢孩子，不想只要一个，但如果生二胎，可能他的工作就保不住了。

他太太生了二胎，是个儿子。但他们一直不敢告诉女儿，那是她弟弟，怕她在外面说漏了嘴，惹出祸来。他们给女儿说，那是农村亲戚的孩子，寄养在他们家，跟她做伴，以后可以在城里上学。他们夫妻对朋友也是这么说。朋友们也不知道那个男孩是他们的儿子，当然在户口上，也不是他们的儿子。

直到她女儿到美国来上学，他们才把实情告诉她，说那不是你表弟，那是你亲弟弟。多年以后，等两个孩子都长大了，他们才可以名正言顺地成为一家人。

那个连生孩子都要偷偷摸摸的国家，据说正在东升西降。

前面一期节目，我们讲中国人口结构性坍塌造成的社会危机。危机的爆发看似突然发生，但在爆发前却经历了一个持续的酝酿过程。细心的听众可能还记得，我们曾引用海明威的名句“gradually, then suddenly”，来描述这个现象。

经济学上有个“多恩布什法则”（“Dornbusch’s Law”），讲的也是危机从缓慢酝酿到突然爆发的规律。Rudi Dornbusch是位经济学家，他的原话说的很直白：“危机的到来，比你想象的要漫长，但是危机一旦到来，发生的比你想象的要快。”

中国的独生子女政策，从拍脑袋定调、开始实施，经过40多年酝酿，到眼下爆发不可逆转的人口危机、社会危机，这个过程完美地验证了“多恩布什法则”。中国人口的结构性坍塌，还有这种坍塌导致的社会危机，比几乎所有权威机构的预测，来得都快。

就在几年前，世界银行还预测中国人口要到2029年才会出现拐点，人口才会开始减少; 中国社科院预估，是到2027年，中国人口才会出现拐点; 就连《经济学人》比较悲观的预测，也认为中国人口至少能撑到2025年，才会出现拐点。

但拐点在三年就发生了。2022年，中国人口开始减少，一发而不可收，连减三年。去年，也就是2024年，中国人口一年就减少了139万。根据上面那些权威机构的预测，中国人口减少的趋势在未来几十年将不断加速。

人口减少可以说是中国的“灰犀牛”——只要睁开眼看，肯定能看到，因为它个头巨大，太显眼，不需要专业知识，就可以看到，就可以做出判断：独生子女政策造成的4-2-1家庭代际结构，四个祖父母、两个父母、一个儿女，肯定会导致人口越来越少。但它不会在一夜之间发生，而是会发生在代际更替之际。

比人口问题减少更深一层的问题是，人口的结构性坍塌，就是我们前面一期节目中分析的，老年人越来越多，年轻人越来越少，社会丧失活力，无力供养已经过了劳动年龄的老年人，养老体制难以为继。

有人说，其他国家也出现了生育率下降，也进入了老龄化社会。我们曾经分析过，其他国家，出生率下降，人口老龄化，是个缓慢的渐进过程，经历了上百年，至少是几十年时间，在进入了发达国家行列之后，才发生的。而中国从轻度老龄化社会进入中度老龄化社会，只用了20来年时间，而且是“未富先老”。

同样是家里4个老人，2个年轻人，如果一家老人有钱，另一家老人没钱，这两家年轻人的养老负担是不一样的。所以，同样是老龄化的两个国家，如果进入老龄化的速度不一样，社会发展程度不一样，并不一定有可比性。党国强制的独生子女政策，人为斩断人口的自然生育规律，造成出生率断崖式下降，人口年龄的结构性坍塌，跟单纯随经济发展而出现的自然生育率降低现象，没有可比性。

在中国，畸形人口结构造成的社会危机，罪魁祸首不是经济发展，而是40多年前武断出台的那个强制“一胎化”政策。

很多中国人有一种误解，以为中国如果不强制“一胎化”，人口早就爆炸了。这种误解的直接来源是党国的宣传洗脑。为了推行独生子女政策，党国宣传机器开足马力，宣传人多的坏处，用“人口爆炸”这种语言恐吓民众。“人口爆炸”的说法不是党国发明的，而是西方学者发明的。

但这种说法，一提出来，在西方就受到广泛质疑。我们下面会讲“人口爆炸”论在西方的遭遇。在这里只提一句，就是在西方，它是一种理论假说，不是放之四海而皆准的真理。有人支持，有人反对，从来没有成为政府制订政策的科学依据。但这样一种假说，到了中国就成了独家真理，不容质疑，而且直接变成了有史以来最激进的国家政策。

Read more